KR20190068251A - Method of Estimating Total Number of the Cheating Players in Online Games - Google Patents

Abstract

According to the present invention, a method of estimating the total number of cheating players in an online game comprises: a hunting site selection process of checking an individual number of players for a plurality of hunting sites existing in the online game and storing information on the hunting sites; and a cheating player estimation process of moving main hunting sites in order, identified in the hunting site selection process, and estimating an individual number of cheating players. Moreover, a sample of cheating players in a game is extracted to estimate the total number and a ratio of the cheating players.

Description

[0001] 1. Field of the Invention [0002] The present invention relates to a method for estimating fraudulent players'

The present invention relates to a method for estimating the number of fraudsters in online games. More particularly, the present invention relates to a method for quickly and accurately estimating the number of fraudsters that cause severe disruption to online game operations. In addition, the present invention relates to a method for estimating the number of fraudulent actors by observing users for a certain period of time in an online game using an ecological estimation method by a single observer in order to minimize time and cost.

Generally, users who play online games want their characters in the game to have enough strength and honor. This aspiration of users is achieved by achieving a high level, or by accumulating a lot of resources in the game. The process of achieving high levels or accumulating lots of resources often requires considerable time and effort, so some users omit them or use automation programs or hacking programs to gain useful information. This behavior is fraudulent and is considered malicious behavior for game publishers and general users.

Also, if the proportion of those who commit fraud exceeds a certain level, the game maker will no longer be able to play normal game services. We introduce a security program such as Anti-Debugger, Memory Protector and Process Protector or CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Human Apart) Various researches have been conducted in terms of client, network, and server in order to analyze, detect, and restrict the play patterns and sequences thereof. However, most of these methods require a considerable amount of time, money, and manpower, so that small game producers can not timely respond to fraudsters.

Therefore, not only the method of judging who is cheating but also the method of estimating the scale of them (the total number) should also be studied, but the research is slower than the method of discrimination.

Accordingly, it is an object of the present invention to provide a method for quickly and efficiently estimating the size and proportion of fraudsters in a game.

Another object of the present invention is to provide a method for assisting small-scale game companies to determine fraudulent actors as formulation time points with minimum time and cost.

According to another aspect of the present invention, there is provided a method for estimating the number of fraudulent actors in an on-line game, comprising the steps of: checking the number of players of a plurality of hunting areas existing in the online game, A hunting game selection process for storing the hunting game; And a cheating player estimating step of estimating the number of cheating players while sequentially moving the main hunting terrain identified in the hunting game selection process. The game player can sample the cheating players in the game and estimate their own number and proportion .

According to an embodiment, the hunting game selection process includes a random hunting game moving process for randomly moving the hunting game targets; An OCR reading process of comparing the NPC (Non-Player Character) names of the players extracted using the OCR reading for each hunting terrain to distinguish the players; And a hunting game DB storing process of storing the corresponding hunting game in the hunting game DB when the number of players is equal to or greater than the first threshold value.

According to one embodiment, the cheating player estimation process may be performed by repeating the screen capturing until the second threshold is reached while moving the hunting terrain based on the hunting game DB.

According to one embodiment, the cheating agent estimating process may include a screen capturing process of performing screen capturing while moving a hunting terrain based on the hunting terrain DB; And an OCR reading process of performing OCR reading on the screen captured image. In the OCR reading process, a nickname of the player who is likely to be the cheater may be extracted, and coordinates of the players may be extracted . ≪ / RTI >

According to an embodiment of the present invention, the irregular agent estimation process may include: an image processing and analysis process for performing image processing and analysis using the extracted screen coordinates and the screen captured image; And a fraudulent agent DB storing step of storing fraudulent agents analyzed through the image processing and analysis among the players in the fraudulent agent DB.

According to an embodiment, the cheating player estimating process may further include a population estimating process of estimating a population size associated with the cheating player for the plurality of hunting games, And may select a game server having the smallest population size among the estimated population sizes for each of the plurality of game servers.

According to one embodiment, the population size is determined by equations (1) to (4), m _t is the number of marked individuals observed at time t, n _t is the number of observed individuals at time t Where s _t is the number of survived individuals at time t, Z _t is the number of individuals observed after time t, , R _t is the number of individuals that survive at time t and are observed again after a certain time.

According to one embodiment, in the population estimation process, the scale estimation of the cheaters may be performed through a capture and a recapture process for the players in the screen-captured image.

According to one embodiment, the scale estimation of the cheaters may be performed by repeating a plurality of sampling processes through the capture and recapture processes. For each of the repeated sampling processes, Estimating the number of individuals with respect to m _t , n _t , and s _t; stopping the sampling process when the estimated number of individuals converges within a predetermined range; and based on the estimated number of converged individuals, The size can be determined.

According to one embodiment, the scale estimation of the cheaters may be performed by repeating a plurality of sampling processes through the capture and recapture processes. For each of the repeated sampling processes, Estimating the number of individuals for m _t , n _t , and s _t , stopping the sampling process based on a variation pattern of the diffusion distribution of the displayed entity through the capturing and re-capturing process, Based on the estimated and converged population, the population size can be determined.

The method of estimating the fraudulent players in the on-line game according to the present invention is advantageous in that the fraudulent players in the game can be sampled and their fractions and the fractions can be estimated.

In addition, the method for estimating fraudulent players in online games according to the present invention is advantageous in that continuity of game service operations can be ensured by preventing deterioration of game service quality that may occur due to fraudsters.

FIG. 1 shows a flowchart of a method for estimating the number of fraudulent actors in an online game according to the present invention.
2 is a block diagram of an online game system according to the present invention.
3 shows a conceptual diagram of a capture and re-capture based sampling method according to the present invention.
4 shows a data set used in the Jolly-Seber estimation according to the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other features and advantages of the present invention will become more apparent from the following detailed description of the present invention when taken in conjunction with the accompanying drawings, It will be possible. The present invention is capable of various modifications and various forms, and specific embodiments are illustrated in the drawings and described in detail in the text. It is to be understood, however, that the invention is not intended to be limited to the particular forms disclosed, but on the contrary, is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

Like reference numerals are used for similar elements in describing each drawing.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. The term "and / or" includes any combination of a plurality of related listed items or any of a plurality of related listed items.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Should not.

The suffix "module "," block ", and "part" for components used in the following description are given or mixed in consideration of ease of specification only and do not have their own distinct meanings or roles .

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

Hereinafter, a method for estimating the number of fraudulent actors in an online game according to the present invention will be described. In this regard, FIG. 1 shows a flowchart of a method for estimating the number of fraudulent actors in an online game according to the present invention. Meanwhile, the method for estimating fraudulent agents in online games according to the present invention can be performed by a server managing a plurality of game servers. In this regard, FIG. 2 shows a configuration diagram of an online game system according to the present invention. As shown in FIG. 2, the online game system 1000 includes a plurality of game servers 100 and a server 200 for managing the game servers 100. Here, in order to distinguish the server 200 from the plurality of game servers 100, the server 200 may be referred to as a central server. In addition, the online game system 1000 may further include a plurality of terminals 300 connected through any one of the plurality of game servers 100. At this time, since it is used by a user who uses an online game of a plurality of terminals 300, the user terminal 300 can be referred to.

In connection with the present invention, terms related to online games will be described in the following Table 1.

Related terms detailed description Characters
(Character)  As an avatar in the game, the character possesses a unique nickname, level, appearance, and things. Bot
(Bot)  It is an automation program designed to perform simple repetitive behaviors in the game instead of players. And Macro. Game nucleus
(Game Hack)  It is a hacking program designed to give a character more than common sense, such as speed-hack, aim-hack, wall-hack and map-hack. In-Game Resources
(In-Game Resource)  In the game money, gold, jewelry, etc., some money is used in the game. In some games, the resources in the game have a good balance through offline cash transactions among the players. Game server
(Game Server)  It is a server that provides game service. Generally, it is composed of multiple channels, and players select a channel to connect to, that is, a server.

Referring again to FIG. 1, a method for estimating the number of fraudulent actors in online games further includes a hunting game selection process S100 and an irregular player estimation process S200. The hunting area selection process S100 and the irregularity person estimation process S200 are performed by the server 200 in FIG. However, the present invention is not limited thereto, and the hunting-terrain selection process S100 and the irregular-agent estimation process S200 may be performed by any one of the UEs shown in FIG. On the other hand, a game server having the smallest population size among the population sizes estimated for each of the plurality of game servers 200 is selected, and accordingly, the terminal 300 receives the online game service through the selected game server have.

The above-mentioned process will be described in detail as follows. In the hunting game selection process (S100), the number of players of the plurality of hunting games existing in the online game is confirmed, and the information about the hunting game is stored. The hunting area selection process S100 may be implemented by software such as an automated macro.

In addition, in the irregular agent estimation process (S200), the number of fraudulent actors is estimated while sequentially moving the main hunting areas identified in the hunting area selection process (S100).

On the other hand, in the hunting game selection process (S100), nicknames of players extracted by using OCR reading and the like are compared with known NPC (non-player character) names such as monsters. When the number of players is equal to or greater than a certain threshold value (#), the hunting terrain DB is stored in the hunting terrain DB.

In this regard, the hunting area selection process S100 includes a random hunting area shifting process S110, an OCR reading process S120, and a hunting area DB storing process S130. In the random hunting game moving process (S110), random movement is performed on the hunting grounds. Further, in the OCR reading process (S120), the NPCs (Non-Player Character) names of the players extracted using the OCR reading for each hunting terrain are compared to distinguish the players. Also, in the hunting game DB storing process (S130), when the number of the players is equal to or larger than the first threshold value, the corresponding hunting game is stored in the hunting game DB.

Next, in the irregular agent estimation process (S200), screen capturing can be repeatedly performed until the second threshold is reached while the hunting terrain is moved based on the hunting terrain DB. In this regard, the second threshold value may be set to a value higher than a first threshold value for storing the hunting game in the hunting game DB when the number of the players of the players is equal to or greater than the first threshold value. That is, in the hunting game selection process (S100), the number of the players is grasped. This is a process corresponding to object detection on the screen. It is a process of distinguishing and detecting a plurality of objects on the screen. Sufficient is enough. On the other hand, in the irregular agent estimating process (S200), a process corresponding to object identification that recognizes whether or not the player is a cheater is performed, and a second threshold with a higher precision can be set. However, since the object detection result associated with the hunter selection process S100 performed previously can be used in the irregular agent estimation process (S200), even though the second threshold value is set higher than the first threshold value, (That is, discrimination of a cheater).

That is, in the cheating agent estimation process (S200), the screen capture is repeatedly performed until the specific threshold value (#) is reached while the hunting game is moved based on the hunting game DB. The captured image automatically extracts the nicknames of the players and the coordinates of the players on the screen using OCR reading or the like. At this time, the nickname suspected to be an unauthorized player is firstly extracted and stored in the fraudster DB. The extracted player coordinate values can be used for more efficient image processing in the image processing and analysis process. Thereafter, if the hunting ground DB is not the last hunting ground, the above process is repeated, and if it is the last hunting ground, the total number of the hunting ground DB is estimated using the stored irregular DB.

More specifically, the irregular agent estimation process (S200) includes a screen capture process (S210), an OCR reading process (S220), an image processing and analysis process (S230), and an irregular person DB storing process (S240) . Also, the irregular agent estimation process (S200) may further include a population estimation process (S250).

In the screen capturing process (S210), screen capturing can be performed while moving the hunting ground based on the hunting game DB. Further, in the OCR reading process (S220), an OCR reading can be performed on the screen captured image. At this time, in the OCR reading process (S220), nicknames of the players who are likely to be cheaters can be extracted and the screen coordinates of the players can be extracted.

In addition, in the image processing and analysis process (S230), image processing and analysis may be performed using the extracted screen coordinates and the screen captured image. Also, in the illegal actor DB storing process (S240), the illegal actor analyzed through the image processing and analysis among the players can be stored in the fraud actor DB.

In addition, in the population estimation process (S250), a population size associated with the cheater may be estimated for a plurality of hunting areas. At this time, the online game may be provided by a plurality of game servers, and a game server having the smallest population size among the estimated population sizes may be selected for each of the plurality of game servers.

Meanwhile, the above-mentioned population size estimation will be described as follows.

In order to quickly and efficiently estimate the scale of in-game cheaters, we use the sampling method based on capture and recapture, which is one of the ecological sampling methods, and the Jolly-Seber estimator considering the characteristics of online games. In this regard, FIG. 3 shows a conceptual diagram of a capture and re-capture based sampling method according to the present invention. As shown in FIG. 3, the observer (operator) estimating the scale of the cheaters in the game extracts fraudulents through the capture step and the recapture step while observing the characters in the online game. The nickname of the character is used as an identifier for identifying the cheater, and the sampling process can be repeated at least five times. We then use the Jolly-Seber estimator and the distribution of fraudsters across the game server to estimate their inheritance.

Meanwhile, the sampling method for ensuring the representativeness of the above-mentioned sample will be described in more detail as follows. In this regard, in order to secure the representativeness of the sample, the extraction target is selected based on the game server or the region (village) in the game, and strict criteria for determining whether or not the player is a fraudulent actor is provided in advance. As described above, an observer estimating the size of fraudsters observes the characters in the online game and extracts the fraudsters through a capture step and a recapture step. Due to the nature of the game, the movement of the characters is free, so all the processes are recorded, and the nickname of the character is recorded afterwards as an identifier for identifying the character. Based on the recorded data, we estimate the total number of Jolly-Seber estimates and distributions of fraudulents across the game server.

Although the ecological sampling method and estimator for estimating the total number vary, there are many differences in the characteristics of online games: (1) high mobility of characters, (2) inability to completely remove characters in the game in general, (3) Capture and re-capture based sampling method and Jolly-Seber estimator are used in view of the free transfer of new characters and existing characters. The number recorded for Jolly-Seber estimates is the number of cheaters that were observed in the previous extraction process, not the number of currently observed cheaters. For example, if we design to have five sampling steps, the number of irregularities recorded in the third extraction process is the number of irregularities found in the first extraction process and the number of irregularities found in the extraction process in the second , And estimates the total number using these data.

Meanwhile, a data set associated with the above-described estimation process will be described as follows. In this regard, Figure 4 shows a dataset used in the Jolly-Seber estimation according to the present invention. Referring to FIG. 4, it is assumed that the distributions of fraudulent agents present in the game server are uniformly distributed. For accurate estimation, a game server among the plurality of game servers is selected. The method of estimating an object size using the Jolly-Seber estimator is shown in Equation 1 below.

Meanwhile, with respect to the entity size estimation of Equation (1), the ratio estimation of the displayed entities is given by Equation (2) below, and the size estimation of the displayed entities is given by Equation (3) below.

Using Equations (2) and (3), the estimation of the scale of the cheaters can be given by Equation (4) below.

With respect to equations (1) to (4), m _t is the number of marked individuals observed at time t and n _t is the number of unmarked individuals observed at time t. Also, s _t is the number of survived individuals at time t, Z _t is the number of individuals observed after time t, t _t is the number of individuals observed after time t, R _t survives at time t, Is the number of individuals that are again observed.

In this regard, Table 2 is a description of the symbols used in the process of estimating the scale of fraudulent actors, such as those described above.

Notation Description m _t  number of observed individuals in time t (number of observed objects observed at time t) u _t  number of unmarked individuals observed in time t (number of unmarked objects observed at time t) n _t number of individuals observed in time t (number of observed objects at time t)
= m _t + u _t s _t number of individuals survived at time t (number of survivors at time t)
= n _t - accidental removals R _t  The number of individuals survived at time t and observed again at some time later. Z _t  number of individuals marked from before time t and observed after time t (number of objects displayed before time t and observed after time t)

Meanwhile, as described above, the population estimation process (S250) is performed through a capture and recapture process for the players in the screen-captured image. More specifically, scale estimation of fraudulent actors may be performed by repeating a plurality of sampling processes through the capture and recapture processes. At this time, it is possible to estimate the number of individuals for the m _t , n _t , and s _t for each of the repeated sampling processes. The repetition of the sampling process related to the estimation of the number of individuals can be repeated a fixed number of times such as 5 times or 10 times as described above. However, it is possible to determine the number of iterations considering the estimation results for more efficient estimation of the number of individuals. In this regard, if the estimated number of individuals converges within a certain range, the sampling process may be stopped and the population size may be determined based on the estimated and converged number of individuals. That is, as shown in Table 2, when the capturing and re-capturing are repeated and the difference in the number of individuals is converged within a certain range based on the number of displayed / not displayed / observed, the sampling process can be stopped. Accordingly, it is possible to identify a fraudulent agent finally based on the finally determined number of entities, and to provide a user's preference, rating of the user among the game servers having the smallest number of fraudulents among a plurality of game servers, Or a real time traffic volume of the game server.

According to another embodiment of the present invention, the sampling process may be stopped based on a variation pattern of the diffusion distribution of the displayed object through the capturing and re-capturing process. That is, as shown in FIG. 4, when the similarity of the change pattern is secured to a certain level or more in consideration of the change pattern of the diffusion distribution of the displayed entity through the capturing and re-capturing process, the sampling process can be stopped. Alternatively, the sampling process can be stopped if the change pattern corresponds to a known change pattern that can be determined to be sufficient for the identification of the irregular actor, taking into account the change pattern of the diffusion distribution of the individual. Accordingly, it is possible to identify a fraudulent agent finally based on the finally determined number of entities, and to provide a user's preference, rating of the user among the game servers having the smallest number of fraudulents among a plurality of game servers, Or a real time traffic volume of the game server.

According to at least one embodiment of the present invention, there is an advantage in that it is possible to sample in-game cheaters and estimate the ratio and the ratio thereof.

Also, according to at least one embodiment of the present invention, there is an advantage that continuity of game service operation can be ensured by preventing deterioration of game service quality that may occur due to fraudulent actors.

According to a software implementation, not only the procedures and functions described herein, but also each component may be implemented as a separate software module. Each of the software modules may perform one or more of the functions and operations described herein. Software code can be implemented in a software application written in a suitable programming language. The software code is stored in a memory and can be executed by a controller or a processor.

1000: Online Game System
100: game servers
200: Server
300:

Claims (10)

In the estimation method of fraudulent players in online games,
A hunting area selection process of confirming the number of players of a plurality of hunting areas existing in the online game and storing information on the hunting area; And
And a cheating player estimating step of estimating the number of cheating players by sequentially moving the main hunting areas identified in the hunting game selection process.
The method according to claim 1,
In the hunting game selection process,
A random hunting movement process for randomly moving the hunting terrain;
An OCR reading process of comparing the NPC (Non-Player Character) names of the players extracted using the OCR reading for each hunting terrain to distinguish the players; And
And a hunting game DB storing the corresponding hunting game in a hunting game DB when the number of players is equal to or greater than a first threshold value.
Estimation of the number of fraudsters in online games.
3. The method of claim 2,
The irregular agent estimation process includes:
And the screen capture is repeatedly performed until the second threshold is reached while the hunting game is being moved based on the hunting game DB.
Estimation of the number of fraudsters in online games.
The method of claim 3,
The irregular agent estimation process includes:
A screen capturing process for performing the screen capturing while moving the hunting terrain based on the hunting terrain DB; And
And an OCR reading step of performing an OCR reading on the screen captured image,
Extracting nicknames of players who are likely to be cheaters, and extracting screen coordinates of the players in the OCR reading process.
Estimation of the number of fraudsters in online games.
5. The method of claim 4,
The irregular agent estimation process includes:
An image processing and analysis process for performing image processing and analysis using the extracted screen coordinates and the screen captured image; And
Further comprising the step of storing a fraudulent agent DB stored in the fraudulent agent database, the fraudulent agent being analyzed through the image processing and analysis among the players,
Estimation of the number of fraudsters in online games.
6. The method of claim 5,
The irregular agent estimation process includes:
Further comprising a population estimating step of estimating a population size associated with the fraudulent agent for the plurality of hunting areas,
Wherein the online game is provided by a plurality of game servers and selects a game server having the smallest population size among the estimated population sizes for each of the plurality of game servers.
Estimation of the number of fraudsters in online games.
The method according to claim 6,
The population size is

Lt; / RTI >

,

Lt; / RTI >
m _t is the number of marked individuals observed at time t, n _t is the number of unmarked individuals observed at time t, s _t is survived individual at time t, Characterized in that Z _t is the number of individuals observed after time t, R _t is the number of individuals observed at a time t and again after a certain time, Z _t is the number of individuals observed after time t, How to Estimate the Number of My Cheaters.
8. The method of claim 7,
In the population estimation process,
The scaling of the fraudulent actors,
And capturing and recapping the players within the screen captured image. ≪ RTI ID = 0.0 >
Estimation of the number of fraudsters in online games.
9. The method of claim 8,
Wherein the scale estimation of the fraudulent actors is characterized by repeating a plurality of sampling processes through the capture and recapture processes,
Estimating the number of individuals for the m _t , n _t , and s _t for each of the repeated sampling steps,
Wherein when the estimated number of users converges within a predetermined range, the sampling process is stopped, and the size of the population is determined based on the estimated and converged number of entities. .
9. The method of claim 8,
Wherein the scale estimation of the fraudulent actors is characterized by repeating a plurality of sampling processes through the capture and recapture processes,
Estimating the number of individuals for the m _t , n _t , and s _t for each of the repeated sampling steps,
And stopping the sampling process based on the variation pattern of the diffusion distribution of the displayed entity through the capturing and re-capturing process and determining the size of the population based on the estimated and converged population As a result,
Estimation of the number of fraudsters in online games.

Images